Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 402 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4622. Min Range: -7.4622
Max Act: 7.4622. Min Act: -0.1700
Data Index: 634276 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4622. Min Range: -7.4622
Max Act: 7.0872. Min Act: -0.1700
Data Index: 6456909 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4622. Min Range: -7.4622
Max Act: 6.9310. Min Act: -0.1700
Data Index: 6637541 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4622. Min Range: -7.4622
Max Act: 6.8997. Min Act: -0.1700
Data Index: 8542634 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4622. Min Range: -7.4622
Max Act: 6.7747. Min Act: -0.1700
Data Index: 1383387 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4622. Min Range: -7.4622
Max Act: 6.8060. Min Act: -0.1700
Data Index: 5804735 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4622. Min Range: -7.4622
Max Act: 6.7435. Min Act: -0.1700
Data Index: 2962904 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4622. Min Range: -7.4622
Max Act: 6.7435. Min Act: -0.1700
Data Index: 4177074 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4622. Min Range: -7.4622
Max Act: 6.7122. Min Act: -0.1700
Data Index: 4988736 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4622. Min Range: -7.4622
Max Act: 6.6810. Min Act: -0.1700
Data Index: 8332120 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4622. Min Range: -7.4622
Max Act: 6.6810. Min Act: -0.1700
Data Index: 480297 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4622. Min Range: -7.4622
Max Act: 6.6497. Min Act: -0.1700
Data Index: 4779951 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4622. Min Range: -7.4622
Max Act: 6.6185. Min Act: -0.1700
Data Index: 6146804 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4622. Min Range: -7.4622
Max Act: 6.5560. Min Act: -0.1700
Data Index: 5709186 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4622. Min Range: -7.4622
Max Act: 6.5560. Min Act: -0.1700
Data Index: 2629427 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4622. Min Range: -7.4622
Max Act: 6.5560. Min Act: -0.1700
Data Index: 5148536 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4622. Min Range: -7.4622
Max Act: 6.5872. Min Act: -0.1700
Data Index: 3312528 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4622. Min Range: -7.4622
Max Act: 6.5560. Min Act: -0.1700
Data Index: 5216289 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4622. Min Range: -7.4622
Max Act: 6.5247. Min Act: -0.1700
Data Index: 7644843 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4622. Min Range: -7.4622
Max Act: 6.5247. Min Act: -0.1700
Data Index: 1437168 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #19